Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
b33cb9a
•
1 Parent(s): 01271b5

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697556550.4aef72135bc5.1113.12 +3 -0
  5. test.tsv +0 -0
  6. training.log +238 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6267818e9af40c1bfdd90ccdaa4fa1556526f644c734e13dca34278e3b64393a
3
+ size 440941957
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 15:32:56 0.0000 0.3164 0.1285 0.5422 0.7872 0.6421 0.4798
3
+ 2 15:36:48 0.0000 0.0989 0.1304 0.5666 0.7059 0.6286 0.4629
4
+ 3 15:40:49 0.0000 0.0781 0.1837 0.5573 0.7620 0.6438 0.4819
5
+ 4 15:44:42 0.0000 0.0542 0.2288 0.5541 0.7975 0.6538 0.4936
6
+ 5 15:48:33 0.0000 0.0409 0.3014 0.5357 0.7643 0.6299 0.4681
7
+ 6 15:52:23 0.0000 0.0285 0.3002 0.5812 0.7620 0.6594 0.5008
8
+ 7 15:56:11 0.0000 0.0194 0.3526 0.5517 0.7998 0.6530 0.4929
9
+ 8 16:00:01 0.0000 0.0129 0.3815 0.5556 0.8112 0.6595 0.4982
10
+ 9 16:03:56 0.0000 0.0077 0.3999 0.5604 0.7746 0.6503 0.4874
11
+ 10 16:07:52 0.0000 0.0052 0.4126 0.5625 0.7826 0.6545 0.4932
runs/events.out.tfevents.1697556550.4aef72135bc5.1113.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07115f14ca00e418ae2bd46599a337e076990cfb37e29fa1ed2b6a5c28d627fa
3
+ size 2030580
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 15:29:10,928 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 15:29:10,930 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): ElectraSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 15:29:10,930 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
48
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
49
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 15:29:10,930 Train: 14465 sentences
51
+ 2023-10-17 15:29:10,930 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 15:29:10,930 Training Params:
54
+ 2023-10-17 15:29:10,930 - learning_rate: "3e-05"
55
+ 2023-10-17 15:29:10,930 - mini_batch_size: "4"
56
+ 2023-10-17 15:29:10,930 - max_epochs: "10"
57
+ 2023-10-17 15:29:10,930 - shuffle: "True"
58
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 15:29:10,930 Plugins:
60
+ 2023-10-17 15:29:10,930 - TensorboardLogger
61
+ 2023-10-17 15:29:10,930 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 15:29:10,930 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 15:29:10,930 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 15:29:10,930 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 15:29:10,931 Computation:
67
+ 2023-10-17 15:29:10,931 - compute on device: cuda:0
68
+ 2023-10-17 15:29:10,931 - embedding storage: none
69
+ 2023-10-17 15:29:10,931 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 15:29:10,931 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 15:29:10,931 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 15:29:10,931 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 15:29:10,931 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 15:29:33,582 epoch 1 - iter 361/3617 - loss 1.95125825 - time (sec): 22.65 - samples/sec: 1618.02 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 15:29:55,459 epoch 1 - iter 722/3617 - loss 1.06563924 - time (sec): 44.53 - samples/sec: 1701.95 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 15:30:17,409 epoch 1 - iter 1083/3617 - loss 0.76511000 - time (sec): 66.48 - samples/sec: 1710.02 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 15:30:39,364 epoch 1 - iter 1444/3617 - loss 0.60696697 - time (sec): 88.43 - samples/sec: 1727.41 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 15:31:01,163 epoch 1 - iter 1805/3617 - loss 0.51265186 - time (sec): 110.23 - samples/sec: 1720.07 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 15:31:23,044 epoch 1 - iter 2166/3617 - loss 0.44808148 - time (sec): 132.11 - samples/sec: 1726.30 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 15:31:44,775 epoch 1 - iter 2527/3617 - loss 0.40140253 - time (sec): 153.84 - samples/sec: 1730.76 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 15:32:07,037 epoch 1 - iter 2888/3617 - loss 0.36462796 - time (sec): 176.10 - samples/sec: 1736.66 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 15:32:28,719 epoch 1 - iter 3249/3617 - loss 0.33777977 - time (sec): 197.79 - samples/sec: 1734.26 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 15:32:50,322 epoch 1 - iter 3610/3617 - loss 0.31676041 - time (sec): 219.39 - samples/sec: 1729.14 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 15:32:50,726 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 15:32:50,727 EPOCH 1 done: loss 0.3164 - lr: 0.000030
86
+ 2023-10-17 15:32:56,275 DEV : loss 0.12850520014762878 - f1-score (micro avg) 0.6421
87
+ 2023-10-17 15:32:56,346 saving best model
88
+ 2023-10-17 15:32:56,847 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 15:33:18,719 epoch 2 - iter 361/3617 - loss 0.10580571 - time (sec): 21.87 - samples/sec: 1777.08 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 15:33:40,709 epoch 2 - iter 722/3617 - loss 0.10075377 - time (sec): 43.86 - samples/sec: 1746.67 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 15:34:02,957 epoch 2 - iter 1083/3617 - loss 0.09535189 - time (sec): 66.11 - samples/sec: 1739.56 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 15:34:24,854 epoch 2 - iter 1444/3617 - loss 0.09554567 - time (sec): 88.00 - samples/sec: 1723.65 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 15:34:46,605 epoch 2 - iter 1805/3617 - loss 0.09771623 - time (sec): 109.76 - samples/sec: 1719.58 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 15:35:08,360 epoch 2 - iter 2166/3617 - loss 0.10009878 - time (sec): 131.51 - samples/sec: 1711.85 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 15:35:31,060 epoch 2 - iter 2527/3617 - loss 0.10203157 - time (sec): 154.21 - samples/sec: 1704.34 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 15:35:55,057 epoch 2 - iter 2888/3617 - loss 0.09981740 - time (sec): 178.21 - samples/sec: 1694.39 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 15:36:17,897 epoch 2 - iter 3249/3617 - loss 0.09868014 - time (sec): 201.05 - samples/sec: 1687.84 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 15:36:40,787 epoch 2 - iter 3610/3617 - loss 0.09884508 - time (sec): 223.94 - samples/sec: 1692.66 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 15:36:41,221 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 15:36:41,222 EPOCH 2 done: loss 0.0989 - lr: 0.000027
101
+ 2023-10-17 15:36:48,360 DEV : loss 0.1303558647632599 - f1-score (micro avg) 0.6286
102
+ 2023-10-17 15:36:48,400 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-17 15:37:12,493 epoch 3 - iter 361/3617 - loss 0.07737891 - time (sec): 24.09 - samples/sec: 1589.18 - lr: 0.000026 - momentum: 0.000000
104
+ 2023-10-17 15:37:36,454 epoch 3 - iter 722/3617 - loss 0.07441406 - time (sec): 48.05 - samples/sec: 1596.55 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 15:38:00,123 epoch 3 - iter 1083/3617 - loss 0.07366381 - time (sec): 71.72 - samples/sec: 1590.65 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 15:38:23,568 epoch 3 - iter 1444/3617 - loss 0.07419654 - time (sec): 95.17 - samples/sec: 1597.42 - lr: 0.000025 - momentum: 0.000000
107
+ 2023-10-17 15:38:45,945 epoch 3 - iter 1805/3617 - loss 0.07452173 - time (sec): 117.54 - samples/sec: 1612.73 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 15:39:09,076 epoch 3 - iter 2166/3617 - loss 0.07529523 - time (sec): 140.67 - samples/sec: 1615.95 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 15:39:32,158 epoch 3 - iter 2527/3617 - loss 0.07621308 - time (sec): 163.76 - samples/sec: 1623.77 - lr: 0.000024 - momentum: 0.000000
110
+ 2023-10-17 15:39:55,149 epoch 3 - iter 2888/3617 - loss 0.07678395 - time (sec): 186.75 - samples/sec: 1621.56 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 15:40:19,157 epoch 3 - iter 3249/3617 - loss 0.07812160 - time (sec): 210.76 - samples/sec: 1613.85 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 15:40:42,962 epoch 3 - iter 3610/3617 - loss 0.07806970 - time (sec): 234.56 - samples/sec: 1617.10 - lr: 0.000023 - momentum: 0.000000
113
+ 2023-10-17 15:40:43,372 ----------------------------------------------------------------------------------------------------
114
+ 2023-10-17 15:40:43,373 EPOCH 3 done: loss 0.0781 - lr: 0.000023
115
+ 2023-10-17 15:40:49,799 DEV : loss 0.18371737003326416 - f1-score (micro avg) 0.6438
116
+ 2023-10-17 15:40:49,840 saving best model
117
+ 2023-10-17 15:40:50,420 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 15:41:13,032 epoch 4 - iter 361/3617 - loss 0.04344296 - time (sec): 22.61 - samples/sec: 1659.04 - lr: 0.000023 - momentum: 0.000000
119
+ 2023-10-17 15:41:36,100 epoch 4 - iter 722/3617 - loss 0.05011872 - time (sec): 45.68 - samples/sec: 1662.49 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 15:41:59,022 epoch 4 - iter 1083/3617 - loss 0.05362355 - time (sec): 68.60 - samples/sec: 1674.43 - lr: 0.000022 - momentum: 0.000000
121
+ 2023-10-17 15:42:22,769 epoch 4 - iter 1444/3617 - loss 0.05564807 - time (sec): 92.35 - samples/sec: 1644.11 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 15:42:46,279 epoch 4 - iter 1805/3617 - loss 0.05342898 - time (sec): 115.86 - samples/sec: 1623.47 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 15:43:08,965 epoch 4 - iter 2166/3617 - loss 0.05432027 - time (sec): 138.54 - samples/sec: 1643.99 - lr: 0.000021 - momentum: 0.000000
124
+ 2023-10-17 15:43:30,566 epoch 4 - iter 2527/3617 - loss 0.05329553 - time (sec): 160.14 - samples/sec: 1656.72 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 15:43:52,348 epoch 4 - iter 2888/3617 - loss 0.05372951 - time (sec): 181.93 - samples/sec: 1663.55 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 15:44:13,841 epoch 4 - iter 3249/3617 - loss 0.05394526 - time (sec): 203.42 - samples/sec: 1677.99 - lr: 0.000020 - momentum: 0.000000
127
+ 2023-10-17 15:44:35,306 epoch 4 - iter 3610/3617 - loss 0.05421478 - time (sec): 224.88 - samples/sec: 1687.06 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 15:44:35,696 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 15:44:35,697 EPOCH 4 done: loss 0.0542 - lr: 0.000020
130
+ 2023-10-17 15:44:42,870 DEV : loss 0.22881226241588593 - f1-score (micro avg) 0.6538
131
+ 2023-10-17 15:44:42,910 saving best model
132
+ 2023-10-17 15:44:43,492 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 15:45:06,049 epoch 5 - iter 361/3617 - loss 0.03180280 - time (sec): 22.56 - samples/sec: 1690.26 - lr: 0.000020 - momentum: 0.000000
134
+ 2023-10-17 15:45:27,669 epoch 5 - iter 722/3617 - loss 0.03588777 - time (sec): 44.17 - samples/sec: 1717.32 - lr: 0.000019 - momentum: 0.000000
135
+ 2023-10-17 15:45:48,939 epoch 5 - iter 1083/3617 - loss 0.04146070 - time (sec): 65.45 - samples/sec: 1726.42 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 15:46:12,476 epoch 5 - iter 1444/3617 - loss 0.03840423 - time (sec): 88.98 - samples/sec: 1696.95 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 15:46:35,825 epoch 5 - iter 1805/3617 - loss 0.03842592 - time (sec): 112.33 - samples/sec: 1673.84 - lr: 0.000018 - momentum: 0.000000
138
+ 2023-10-17 15:46:57,750 epoch 5 - iter 2166/3617 - loss 0.03790309 - time (sec): 134.26 - samples/sec: 1675.11 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 15:47:19,326 epoch 5 - iter 2527/3617 - loss 0.04008082 - time (sec): 155.83 - samples/sec: 1692.22 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 15:47:42,076 epoch 5 - iter 2888/3617 - loss 0.03976002 - time (sec): 178.58 - samples/sec: 1690.27 - lr: 0.000017 - momentum: 0.000000
141
+ 2023-10-17 15:48:04,606 epoch 5 - iter 3249/3617 - loss 0.04136127 - time (sec): 201.11 - samples/sec: 1692.09 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 15:48:26,428 epoch 5 - iter 3610/3617 - loss 0.04096447 - time (sec): 222.93 - samples/sec: 1701.22 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 15:48:26,886 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 15:48:26,887 EPOCH 5 done: loss 0.0409 - lr: 0.000017
145
+ 2023-10-17 15:48:33,200 DEV : loss 0.30138152837753296 - f1-score (micro avg) 0.6299
146
+ 2023-10-17 15:48:33,240 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 15:48:55,394 epoch 6 - iter 361/3617 - loss 0.02934544 - time (sec): 22.15 - samples/sec: 1719.54 - lr: 0.000016 - momentum: 0.000000
148
+ 2023-10-17 15:49:17,504 epoch 6 - iter 722/3617 - loss 0.02571943 - time (sec): 44.26 - samples/sec: 1685.96 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 15:49:39,822 epoch 6 - iter 1083/3617 - loss 0.02841514 - time (sec): 66.58 - samples/sec: 1690.02 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 15:50:02,839 epoch 6 - iter 1444/3617 - loss 0.02630164 - time (sec): 89.60 - samples/sec: 1700.67 - lr: 0.000015 - momentum: 0.000000
151
+ 2023-10-17 15:50:25,636 epoch 6 - iter 1805/3617 - loss 0.02616624 - time (sec): 112.39 - samples/sec: 1689.51 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 15:50:47,660 epoch 6 - iter 2166/3617 - loss 0.02849047 - time (sec): 134.42 - samples/sec: 1697.10 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 15:51:09,936 epoch 6 - iter 2527/3617 - loss 0.02883754 - time (sec): 156.69 - samples/sec: 1683.02 - lr: 0.000014 - momentum: 0.000000
154
+ 2023-10-17 15:51:32,228 epoch 6 - iter 2888/3617 - loss 0.02863689 - time (sec): 178.99 - samples/sec: 1686.43 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 15:51:54,353 epoch 6 - iter 3249/3617 - loss 0.02895811 - time (sec): 201.11 - samples/sec: 1691.66 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 15:52:16,274 epoch 6 - iter 3610/3617 - loss 0.02847322 - time (sec): 223.03 - samples/sec: 1700.56 - lr: 0.000013 - momentum: 0.000000
157
+ 2023-10-17 15:52:16,684 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 15:52:16,685 EPOCH 6 done: loss 0.0285 - lr: 0.000013
159
+ 2023-10-17 15:52:23,863 DEV : loss 0.3001513183116913 - f1-score (micro avg) 0.6594
160
+ 2023-10-17 15:52:23,903 saving best model
161
+ 2023-10-17 15:52:24,490 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 15:52:46,074 epoch 7 - iter 361/3617 - loss 0.02066184 - time (sec): 21.58 - samples/sec: 1680.61 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 15:53:07,793 epoch 7 - iter 722/3617 - loss 0.01708605 - time (sec): 43.30 - samples/sec: 1686.78 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-17 15:53:29,760 epoch 7 - iter 1083/3617 - loss 0.01965216 - time (sec): 65.27 - samples/sec: 1679.03 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 15:53:52,055 epoch 7 - iter 1444/3617 - loss 0.01952788 - time (sec): 87.56 - samples/sec: 1697.54 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 15:54:14,114 epoch 7 - iter 1805/3617 - loss 0.02017047 - time (sec): 109.62 - samples/sec: 1720.19 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 15:54:36,183 epoch 7 - iter 2166/3617 - loss 0.02020291 - time (sec): 131.69 - samples/sec: 1730.58 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 15:54:58,335 epoch 7 - iter 2527/3617 - loss 0.01975895 - time (sec): 153.84 - samples/sec: 1723.15 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 15:55:20,465 epoch 7 - iter 2888/3617 - loss 0.01957773 - time (sec): 175.97 - samples/sec: 1718.41 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 15:55:42,750 epoch 7 - iter 3249/3617 - loss 0.01965841 - time (sec): 198.26 - samples/sec: 1717.48 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 15:56:04,884 epoch 7 - iter 3610/3617 - loss 0.01945380 - time (sec): 220.39 - samples/sec: 1720.30 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-17 15:56:05,307 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 15:56:05,307 EPOCH 7 done: loss 0.0194 - lr: 0.000010
174
+ 2023-10-17 15:56:11,598 DEV : loss 0.3526001274585724 - f1-score (micro avg) 0.653
175
+ 2023-10-17 15:56:11,642 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 15:56:34,023 epoch 8 - iter 361/3617 - loss 0.01442396 - time (sec): 22.38 - samples/sec: 1663.89 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-17 15:56:56,449 epoch 8 - iter 722/3617 - loss 0.01297978 - time (sec): 44.81 - samples/sec: 1646.69 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-17 15:57:19,213 epoch 8 - iter 1083/3617 - loss 0.01197713 - time (sec): 67.57 - samples/sec: 1644.68 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 15:57:42,219 epoch 8 - iter 1444/3617 - loss 0.01296548 - time (sec): 90.58 - samples/sec: 1661.07 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 15:58:04,626 epoch 8 - iter 1805/3617 - loss 0.01361106 - time (sec): 112.98 - samples/sec: 1668.32 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-17 15:58:26,765 epoch 8 - iter 2166/3617 - loss 0.01333120 - time (sec): 135.12 - samples/sec: 1671.29 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 15:58:48,975 epoch 8 - iter 2527/3617 - loss 0.01337065 - time (sec): 157.33 - samples/sec: 1681.32 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 15:59:11,245 epoch 8 - iter 2888/3617 - loss 0.01298466 - time (sec): 179.60 - samples/sec: 1687.72 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-17 15:59:32,888 epoch 8 - iter 3249/3617 - loss 0.01264441 - time (sec): 201.24 - samples/sec: 1687.78 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 15:59:54,791 epoch 8 - iter 3610/3617 - loss 0.01285488 - time (sec): 223.15 - samples/sec: 1698.74 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 15:59:55,221 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 15:59:55,221 EPOCH 8 done: loss 0.0129 - lr: 0.000007
188
+ 2023-10-17 16:00:01,661 DEV : loss 0.38147813081741333 - f1-score (micro avg) 0.6595
189
+ 2023-10-17 16:00:01,703 saving best model
190
+ 2023-10-17 16:00:02,302 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 16:00:24,155 epoch 9 - iter 361/3617 - loss 0.00411798 - time (sec): 21.85 - samples/sec: 1665.06 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 16:00:45,993 epoch 9 - iter 722/3617 - loss 0.00798323 - time (sec): 43.69 - samples/sec: 1695.04 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 16:01:08,507 epoch 9 - iter 1083/3617 - loss 0.00861031 - time (sec): 66.20 - samples/sec: 1696.57 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 16:01:32,055 epoch 9 - iter 1444/3617 - loss 0.00771193 - time (sec): 89.75 - samples/sec: 1681.98 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 16:01:53,809 epoch 9 - iter 1805/3617 - loss 0.00769213 - time (sec): 111.51 - samples/sec: 1693.76 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 16:02:16,235 epoch 9 - iter 2166/3617 - loss 0.00792339 - time (sec): 133.93 - samples/sec: 1694.24 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 16:02:39,818 epoch 9 - iter 2527/3617 - loss 0.00790490 - time (sec): 157.51 - samples/sec: 1695.75 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 16:03:02,857 epoch 9 - iter 2888/3617 - loss 0.00773309 - time (sec): 180.55 - samples/sec: 1691.08 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 16:03:27,163 epoch 9 - iter 3249/3617 - loss 0.00781997 - time (sec): 204.86 - samples/sec: 1673.25 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 16:03:50,243 epoch 9 - iter 3610/3617 - loss 0.00767986 - time (sec): 227.94 - samples/sec: 1663.71 - lr: 0.000003 - momentum: 0.000000
201
+ 2023-10-17 16:03:50,696 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 16:03:50,697 EPOCH 9 done: loss 0.0077 - lr: 0.000003
203
+ 2023-10-17 16:03:56,943 DEV : loss 0.39987462759017944 - f1-score (micro avg) 0.6503
204
+ 2023-10-17 16:03:56,984 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 16:04:19,198 epoch 10 - iter 361/3617 - loss 0.00449363 - time (sec): 22.21 - samples/sec: 1699.38 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-17 16:04:42,363 epoch 10 - iter 722/3617 - loss 0.00614855 - time (sec): 45.38 - samples/sec: 1718.53 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 16:05:06,457 epoch 10 - iter 1083/3617 - loss 0.00541348 - time (sec): 69.47 - samples/sec: 1661.47 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-17 16:05:29,935 epoch 10 - iter 1444/3617 - loss 0.00603835 - time (sec): 92.95 - samples/sec: 1651.51 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 16:05:52,494 epoch 10 - iter 1805/3617 - loss 0.00569937 - time (sec): 115.51 - samples/sec: 1642.98 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 16:06:15,075 epoch 10 - iter 2166/3617 - loss 0.00554871 - time (sec): 138.09 - samples/sec: 1654.28 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 16:06:37,223 epoch 10 - iter 2527/3617 - loss 0.00529464 - time (sec): 160.24 - samples/sec: 1664.53 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 16:07:00,170 epoch 10 - iter 2888/3617 - loss 0.00525690 - time (sec): 183.18 - samples/sec: 1661.69 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 16:07:22,855 epoch 10 - iter 3249/3617 - loss 0.00525983 - time (sec): 205.87 - samples/sec: 1667.90 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 16:07:45,081 epoch 10 - iter 3610/3617 - loss 0.00525246 - time (sec): 228.09 - samples/sec: 1663.75 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 16:07:45,507 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 16:07:45,508 EPOCH 10 done: loss 0.0052 - lr: 0.000000
217
+ 2023-10-17 16:07:52,788 DEV : loss 0.4126187264919281 - f1-score (micro avg) 0.6545
218
+ 2023-10-17 16:07:53,330 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 16:07:53,332 Loading model from best epoch ...
220
+ 2023-10-17 16:07:55,106 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
221
+ 2023-10-17 16:08:03,374
222
+ Results:
223
+ - F-score (micro) 0.6596
224
+ - F-score (macro) 0.5329
225
+ - Accuracy 0.5036
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ loc 0.6219 0.8156 0.7057 591
231
+ pers 0.5813 0.7815 0.6667 357
232
+ org 0.2250 0.2278 0.2264 79
233
+
234
+ micro avg 0.5835 0.7585 0.6596 1027
235
+ macro avg 0.4761 0.6083 0.5329 1027
236
+ weighted avg 0.5773 0.7585 0.6553 1027
237
+
238
+ 2023-10-17 16:08:03,374 ----------------------------------------------------------------------------------------------------